I'm very happy to announce that the paper "Delaunay Graph: Addressing Over-Squashing and Over-Smoothing Using Delaunay Triangulation" authored by Hugo Attali, myself and Nathalie Pernelle has been accepted at #ICML2024 !!! Congratulations Hugo for your hard work!
New low in reviewing quality:
R3:"why didn't you test your method on dataset X and Y?"
-> results for datasets X and Y are in the result table
I mean, it doesn't even require one to have read the paper, just a look at the tables and figures...
(this is at KDD btw)
Our new short course, Knowledge Graphs for RAG, is now available! Knowledge graphs are a data structure that is great at capturing complex relationships between data of multiple types. By enabling more sophisticated retrieval of text than similarity search alone, knowledge graphs can improve the context you pass to the LLM and the performance of your RAG applications.
In this course, taught by @akollegger of @neo4j, you’ll
- Explore how knowledge graphs work by building a graph of public financial documents from scratch
- Learn to write queries that retrieve text and data from the graph and use it to enhance the context you pass to an LLM chatbot
- Combine a knowledge graph with a question-answer chain to build better RAG-powered chat systems
Sign up here! https://t.co/N3gceKrvib
Two papers accepted:
"Matrice d'adjacence courbée : intégration de la courbure dans la transmission des messages" at EGC2024 with Hugo Attali and Nathalie Pernelle
.. and
"Citation Prediction by Leveraging Transformers and Natural Language Processing Heuristics" in Information Processing and Management with @diegoref@FraOsborne Danilo Dessi and Marco Murgia